Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:
 "This is the material which was staged after willystuff in linux-next.

  Subsystems affected by this patch series: mm (debug, selftests,
  pagecache, thp, rmap, migration, kasan, hugetlb, pagemap, madvise),
  and selftests"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (113 commits)
  selftests: kselftest framework: provide "finished" helper
  mm: madvise: MADV_DONTNEED_LOCKED
  mm: fix race between MADV_FREE reclaim and blkdev direct IO read
  mm: generalize ARCH_HAS_FILTER_PGPROT
  mm: unmap_mapping_range_tree() with i_mmap_rwsem shared
  mm: warn on deleting redirtied only if accounted
  mm/huge_memory: remove stale locking logic from __split_huge_pmd()
  mm/huge_memory: remove stale page_trans_huge_mapcount()
  mm/swapfile: remove stale reuse_swap_page()
  mm/khugepaged: remove reuse_swap_page() usage
  mm/huge_memory: streamline COW logic in do_huge_pmd_wp_page()
  mm: streamline COW logic in do_swap_page()
  mm: slightly clarify KSM logic in do_swap_page()
  mm: optimize do_wp_page() for fresh pages in local LRU pagevecs
  mm: optimize do_wp_page() for exclusive pages in the swapcache
  mm/huge_memory: make is_transparent_hugepage() static
  userfaultfd/selftests: enable hugetlb remap and remove event testing
  selftests/vm: add hugetlb madvise MADV_DONTNEED MADV_REMOVE test
  mm: enable MADV_DONTNEED for hugetlb mappings
  kasan: disable LOCKDEP when printing reports
  ...

12 files changed, 992 insertions, 171 deletions

diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index f1180987492c..b8f248018174 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -28,6 +28,7 @@
  *
  * When all tests are finished, clean up and exit the program with one of:
  *
+ *    ksft_finished();
  *    ksft_exit(condition);
  *    ksft_exit_pass();
  *    ksft_exit_fail();
@@ -235,6 +236,15 @@ static inline int ksft_exit_fail(void)
 		ksft_exit_fail();	\
 	} while (0)
 
+/**
+ * ksft_finished() - Exit selftest with success if all tests passed
+ */
+#define ksft_finished()			\
+	ksft_exit(ksft_plan ==		\
+		  ksft_cnt.ksft_pass +	\
+		  ksft_cnt.ksft_xfail +	\
+		  ksft_cnt.ksft_xskip)
+
 static inline int ksft_exit_fail_msg(const char *msg, ...)
 {
 	int saved_errno = errno;
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 3b5faec3c04f..d7507f3c7c76 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -3,6 +3,7 @@ hugepage-mmap
 hugepage-mremap
 hugepage-shm
 hugepage-vmemmap
+hugetlb-madvise
 khugepaged
 map_hugetlb
 map_populate
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index fbf390b51c2f..04a49e876a46 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -30,6 +30,7 @@ LDLIBS = -lrt -lpthread
 TEST_GEN_FILES = compaction_test
 TEST_GEN_FILES += gup_test
 TEST_GEN_FILES += hmm-tests
+TEST_GEN_FILES += hugetlb-madvise
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-mremap
 TEST_GEN_FILES += hugepage-shm
diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c
index fe043f67798b..cda837a14736 100644
--- a/tools/testing/selftests/vm/gup_test.c
+++ b/tools/testing/selftests/vm/gup_test.c
@@ -10,8 +10,9 @@
 #include <assert.h>
 #include "../../../../mm/gup_test.h"
 
+#include "util.h"
+
 #define MB (1UL << 20)
-#define PAGE_SIZE sysconf(_SC_PAGESIZE)
 
 /* Just the flags we need, copied from mm.h: */
 #define FOLL_WRITE	0x01	/* check pte is writable */
diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c
new file mode 100644
index 000000000000..6c6af40f5747
--- /dev/null
+++ b/tools/testing/selftests/vm/hugetlb-madvise.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * hugepage-madvise:
+ *
+ * Basic functional testing of madvise MADV_DONTNEED and MADV_REMOVE
+ * on hugetlb mappings.
+ *
+ * Before running this test, make sure the administrator has pre-allocated
+ * at least MIN_FREE_PAGES hugetlb pages and they are free.  In addition,
+ * the test takes an argument that is the path to a file in a hugetlbfs
+ * filesystem.  Therefore, a hugetlbfs filesystem must be mounted on some
+ * directory.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#define __USE_GNU
+#include <fcntl.h>
+
+#define USAGE	"USAGE: %s <hugepagefile_name>\n"
+#define MIN_FREE_PAGES	20
+#define NR_HUGE_PAGES	10	/* common number of pages to map/allocate */
+
+#define validate_free_pages(exp_free)					\
+	do {								\
+		int fhp = get_free_hugepages();				\
+		if (fhp != (exp_free)) {				\
+			printf("Unexpected number of free huge "	\
+				"pages line %d\n", __LINE__);		\
+			exit(1);					\
+		}							\
+	} while (0)
+
+unsigned long huge_page_size;
+unsigned long base_page_size;
+
+/*
+ * default_huge_page_size copied from mlock2-tests.c
+ */
+unsigned long default_huge_page_size(void)
+{
+	unsigned long hps = 0;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+
+	if (!f)
+		return 0;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+			hps <<= 10;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(f);
+	return hps;
+}
+
+unsigned long get_free_hugepages(void)
+{
+	unsigned long fhp = 0;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+
+	if (!f)
+		return fhp;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "HugePages_Free:      %lu", &fhp) == 1)
+			break;
+	}
+
+	free(line);
+	fclose(f);
+	return fhp;
+}
+
+void write_fault_pages(void *addr, unsigned long nr_pages)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; i++)
+		*((unsigned long *)(addr + (i * huge_page_size))) = i;
+}
+
+void read_fault_pages(void *addr, unsigned long nr_pages)
+{
+	unsigned long i, tmp;
+
+	for (i = 0; i < nr_pages; i++)
+		tmp += *((unsigned long *)(addr + (i * huge_page_size)));
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long free_hugepages;
+	void *addr, *addr2;
+	int fd;
+	int ret;
+
+	if (argc != 2) {
+		printf(USAGE, argv[0]);
+		exit(1);
+	}
+
+	huge_page_size = default_huge_page_size();
+	if (!huge_page_size) {
+		printf("Unable to determine huge page size, exiting!\n");
+		exit(1);
+	}
+	base_page_size = sysconf(_SC_PAGE_SIZE);
+	if (!huge_page_size) {
+		printf("Unable to determine base page size, exiting!\n");
+		exit(1);
+	}
+
+	free_hugepages = get_free_hugepages();
+	if (free_hugepages < MIN_FREE_PAGES) {
+		printf("Not enough free huge pages to test, exiting!\n");
+		exit(1);
+	}
+
+	fd = open(argv[1], O_CREAT | O_RDWR, 0755);
+	if (fd < 0) {
+		perror("Open failed");
+		exit(1);
+	}
+
+	/*
+	 * Test validity of MADV_DONTNEED addr and length arguments.  mmap
+	 * size is NR_HUGE_PAGES + 2.  One page at the beginning and end of
+	 * the mapping will be unmapped so we KNOW there is nothing mapped
+	 * there.
+	 */
+	addr = mmap(NULL, (NR_HUGE_PAGES + 2) * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+			-1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+	if (munmap(addr, huge_page_size) ||
+			munmap(addr + (NR_HUGE_PAGES + 1) * huge_page_size,
+				huge_page_size)) {
+		perror("munmap");
+		exit(1);
+	}
+	addr = addr + huge_page_size;
+
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* addr before mapping should fail */
+	ret = madvise(addr - base_page_size, NR_HUGE_PAGES * huge_page_size,
+		MADV_DONTNEED);
+	if (!ret) {
+		printf("Unexpected success of madvise call with invalid addr line %d\n",
+				__LINE__);
+			exit(1);
+	}
+
+	/* addr + length after mapping should fail */
+	ret = madvise(addr, (NR_HUGE_PAGES * huge_page_size) + base_page_size,
+		MADV_DONTNEED);
+	if (!ret) {
+		printf("Unexpected success of madvise call with invalid length line %d\n",
+				__LINE__);
+			exit(1);
+	}
+
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+
+	/*
+	 * Test alignment of MADV_DONTNEED addr and length arguments
+	 */
+	addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+			-1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* addr is not huge page size aligned and should fail */
+	ret = madvise(addr + base_page_size,
+			NR_HUGE_PAGES * huge_page_size - base_page_size,
+			MADV_DONTNEED);
+	if (!ret) {
+		printf("Unexpected success of madvise call with unaligned start address %d\n",
+				__LINE__);
+			exit(1);
+	}
+
+	/* addr + length should be aligned up to huge page size */
+	if (madvise(addr,
+			((NR_HUGE_PAGES - 1) * huge_page_size) + base_page_size,
+			MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+
+	/* should free all pages in mapping */
+	validate_free_pages(free_hugepages);
+
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+
+	/*
+	 * Test MADV_DONTNEED on anonymous private mapping
+	 */
+	addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+			-1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+
+	/* should free all pages in mapping */
+	validate_free_pages(free_hugepages);
+
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+
+	/*
+	 * Test MADV_DONTNEED on private mapping of hugetlb file
+	 */
+	if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) {
+		perror("fallocate");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	/* read should not consume any pages */
+	read_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* madvise should not free any pages */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* writes should allocate private pages */
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES));
+
+	/* madvise should free private pages */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* writes should allocate private pages */
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES));
+
+	/*
+	 * The fallocate below certainly should free the pages associated
+	 * with the file.  However, pages in the private mapping are also
+	 * freed.  This is not the 'correct' behavior, but is expected
+	 * because this is how it has worked since the initial hugetlb
+	 * implementation.
+	 */
+	if (fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+					0, NR_HUGE_PAGES * huge_page_size)) {
+		perror("fallocate");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages);
+
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+
+	/*
+	 * Test MADV_DONTNEED on shared mapping of hugetlb file
+	 */
+	if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) {
+		perror("fallocate");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	/* write should not consume any pages */
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* madvise should not free any pages */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/*
+	 * Test MADV_REMOVE on shared mapping of hugetlb file
+	 *
+	 * madvise is same as hole punch and should free all pages.
+	 */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages);
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+
+	/*
+	 * Test MADV_REMOVE on shared and private mapping of hugetlb file
+	 */
+	if (fallocate(fd, 0, 0, NR_HUGE_PAGES * huge_page_size)) {
+		perror("fallocate");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	addr = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	/* shared write should not consume any additional pages */
+	write_fault_pages(addr, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	addr2 = mmap(NULL, NR_HUGE_PAGES * huge_page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE, fd, 0);
+	if (addr2 == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	/* private read should not consume any pages */
+	read_fault_pages(addr2, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* private write should consume additional pages */
+	write_fault_pages(addr2, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES));
+
+	/* madvise of shared mapping should not free any pages */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES));
+
+	/* madvise of private mapping should free private pages */
+	if (madvise(addr2, NR_HUGE_PAGES * huge_page_size, MADV_DONTNEED)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages - NR_HUGE_PAGES);
+
+	/* private write should consume additional pages again */
+	write_fault_pages(addr2, NR_HUGE_PAGES);
+	validate_free_pages(free_hugepages - (2 * NR_HUGE_PAGES));
+
+	/*
+	 * madvise should free both file and private pages although this is
+	 * not correct.  private pages should not be freed, but this is
+	 * expected.  See comment associated with FALLOC_FL_PUNCH_HOLE call.
+	 */
+	if (madvise(addr, NR_HUGE_PAGES * huge_page_size, MADV_REMOVE)) {
+		perror("madvise");
+		exit(1);
+	}
+	validate_free_pages(free_hugepages);
+
+	(void)munmap(addr, NR_HUGE_PAGES * huge_page_size);
+	(void)munmap(addr2, NR_HUGE_PAGES * huge_page_size);
+
+	close(fd);
+	unlink(argv[1]);
+	return 0;
+}
diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c
index 1436e1a9a3d3..fd85f15869d1 100644
--- a/tools/testing/selftests/vm/ksm_tests.c
+++ b/tools/testing/selftests/vm/ksm_tests.c
@@ -12,6 +12,7 @@
 
 #include "../kselftest.h"
 #include "../../../../include/vdso/time64.h"
+#include "util.h"
 
 #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/"
 #define KSM_FP(s) (KSM_SYSFS_PATH s)
@@ -22,15 +23,6 @@
 #define KSM_MERGE_ACROSS_NODES_DEFAULT true
 #define MB (1ul << 20)
 
-#define PAGE_SHIFT 12
-#define HPAGE_SHIFT 21
-
-#define PAGE_SIZE (1 << PAGE_SHIFT)
-#define HPAGE_SIZE (1 << HPAGE_SHIFT)
-
-#define PAGEMAP_PRESENT(ent)	(((ent) & (1ull << 63)) != 0)
-#define PAGEMAP_PFN(ent)	((ent) & ((1ull << 55) - 1))
-
 struct ksm_sysfs {
 	unsigned long max_page_sharing;
 	unsigned long merge_across_nodes;
@@ -456,34 +448,6 @@ err_out:
 	return KSFT_FAIL;
 }
 
-int64_t allocate_transhuge(void *ptr, int pagemap_fd)
-{
-	uint64_t ent[2];
-
-	/* drop pmd */
-	if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
-				MAP_FIXED | MAP_ANONYMOUS |
-				MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
-		errx(2, "mmap transhuge");
-
-	if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
-		err(2, "MADV_HUGEPAGE");
-
-	/* allocate transparent huge page */
-	*(volatile void **)ptr = ptr;
-
-	if (pread(pagemap_fd, ent, sizeof(ent),
-			(uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
-		err(2, "read pagemap");
-
-	if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
-	    PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
-	    !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
-		return PAGEMAP_PFN(ent[0]);
-
-	return -1;
-}
-
 static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size)
 {
 	void *map_ptr, *map_ptr_orig;
diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c
index 93e7e7ffed33..957b9e18c729 100644
--- a/tools/testing/selftests/vm/memfd_secret.c
+++ b/tools/testing/selftests/vm/memfd_secret.c
@@ -282,7 +282,7 @@ int main(int argc, char *argv[])
 
 	close(fd);
 
-	ksft_exit(!ksft_get_fail_cnt());
+	ksft_finished();
 }
 
 #else /* __NR_memfd_secret */
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index e10d50e0b8e8..3b265f140c25 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -131,6 +131,18 @@ else
 	echo "[PASS]"
 fi
 
+echo "-----------------------"
+echo "running hugetlb-madvise"
+echo "-----------------------"
+./hugetlb-madvise $mnt/madvise-test
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+rm -f $mnt/madvise-test
+
 echo "NOTE: The above hugetlb tests provide minimal coverage.  Use"
 echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
 echo "      hugetlb regression testing."
@@ -196,14 +208,13 @@ echo "running userfaultfd_hugetlb"
 echo "---------------------------"
 # Test requires source and destination huge pages.  Size of source
 # (half_ufd_size_MB) is passed as argument to test.
-./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file
+./userfaultfd hugetlb $half_ufd_size_MB 32
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1
 else
 	echo "[PASS]"
 fi
-rm -f $mnt/ufd_test_file
 
 echo "-------------------------"
 echo "running userfaultfd_shmem"
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
index a03cb3fce1f6..e3f00adb1b82 100644
--- a/tools/testing/selftests/vm/transhuge-stress.c
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -15,48 +15,12 @@
 #include <fcntl.h>
 #include <string.h>
 #include <sys/mman.h>
+#include "util.h"
 
-#define PAGE_SHIFT 12
-#define HPAGE_SHIFT 21
-
-#define PAGE_SIZE (1 << PAGE_SHIFT)
-#define HPAGE_SIZE (1 << HPAGE_SHIFT)
-
-#define PAGEMAP_PRESENT(ent)	(((ent) & (1ull << 63)) != 0)
-#define PAGEMAP_PFN(ent)	((ent) & ((1ull << 55) - 1))
-
-int pagemap_fd;
 int backing_fd = -1;
 int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE;
 #define PROT_RW (PROT_READ | PROT_WRITE)
 
-int64_t allocate_transhuge(void *ptr)
-{
-	uint64_t ent[2];
-
-	/* drop pmd */
-	if (mmap(ptr, HPAGE_SIZE, PROT_RW, MAP_FIXED | mmap_flags,
-		 backing_fd, 0) != ptr)
-		errx(2, "mmap transhuge");
-
-	if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
-		err(2, "MADV_HUGEPAGE");
-
-	/* allocate transparent huge page */
-	*(volatile void **)ptr = ptr;
-
-	if (pread(pagemap_fd, ent, sizeof(ent),
-			(uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
-		err(2, "read pagemap");
-
-	if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
-	    PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
-	    !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
-		return PAGEMAP_PFN(ent[0]);
-
-	return -1;
-}
-
 int main(int argc, char **argv)
 {
 	size_t ram, len;
@@ -67,6 +31,7 @@ int main(int argc, char **argv)
 	double s;
 	uint8_t *map;
 	size_t map_len;
+	int pagemap_fd;
 
 	ram = sysconf(_SC_PHYS_PAGES);
 	if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4)
@@ -122,7 +87,7 @@ int main(int argc, char **argv)
 		for (p = ptr; p < ptr + len; p += HPAGE_SIZE) {
 			int64_t pfn;
 
-			pfn = allocate_transhuge(p);
+			pfn = allocate_transhuge(p, pagemap_fd);
 
 			if (pfn < 0) {
 				nr_failed++;
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 39403b8931de..92a4516f8f0d 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -89,7 +89,6 @@ static bool test_uffdio_minor = false;
 static bool map_shared;
 static int shm_fd;
 static int huge_fd;
-static char *huge_fd_off0;
 static unsigned long long *count_verify;
 static int uffd = -1;
 static int uffd_flags, finished, *pipefd;
@@ -128,9 +127,9 @@ const char *examples =
     "./userfaultfd anon 100 99999\n\n"
     "# Run share memory test on 1GiB region with 99 bounces:\n"
     "./userfaultfd shmem 1000 99\n\n"
-    "# Run hugetlb memory test on 256MiB region with 50 bounces (using /dev/hugepages/hugefile):\n"
-    "./userfaultfd hugetlb 256 50 /dev/hugepages/hugefile\n\n"
-    "# Run the same hugetlb test but using shmem:\n"
+    "# Run hugetlb memory test on 256MiB region with 50 bounces:\n"
+    "./userfaultfd hugetlb 256 50\n\n"
+    "# Run the same hugetlb test but using shared file:\n"
     "./userfaultfd hugetlb_shared 256 50 /dev/hugepages/hugefile\n\n"
     "# 10MiB-~6GiB 999 bounces anonymous test, "
     "continue forever unless an error triggers\n"
@@ -227,10 +226,13 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
 
 static void hugetlb_release_pages(char *rel_area)
 {
-	if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-		      rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
-		      nr_pages * page_size))
-		err("fallocate() failed");
+	if (!map_shared) {
+		if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED))
+			err("madvise(MADV_DONTNEED) failed");
+	} else {
+		if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE))
+			err("madvise(MADV_REMOVE) failed");
+	}
 }
 
 static void hugetlb_allocate_area(void **alloc_area)
@@ -238,26 +240,37 @@ static void hugetlb_allocate_area(void **alloc_area)
 	void *area_alias = NULL;
 	char **alloc_area_alias;
 
-	*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-			   (map_shared ? MAP_SHARED : MAP_PRIVATE) |
-			   MAP_HUGETLB |
-			   (*alloc_area == area_src ? 0 : MAP_NORESERVE),
-			   huge_fd, *alloc_area == area_src ? 0 :
-			   nr_pages * page_size);
+	if (!map_shared)
+		*alloc_area = mmap(NULL,
+			nr_pages * page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB |
+				(*alloc_area == area_src ? 0 : MAP_NORESERVE),
+			-1,
+			0);
+	else
+		*alloc_area = mmap(NULL,
+			nr_pages * page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_SHARED |
+				(*alloc_area == area_src ? 0 : MAP_NORESERVE),
+			huge_fd,
+			*alloc_area == area_src ? 0 : nr_pages * page_size);
 	if (*alloc_area == MAP_FAILED)
 		err("mmap of hugetlbfs file failed");
 
 	if (map_shared) {
-		area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
-				  MAP_SHARED | MAP_HUGETLB,
-				  huge_fd, *alloc_area == area_src ? 0 :
-				  nr_pages * page_size);
+		area_alias = mmap(NULL,
+			nr_pages * page_size,
+			PROT_READ | PROT_WRITE,
+			MAP_SHARED,
+			huge_fd,
+			*alloc_area == area_src ? 0 : nr_pages * page_size);
 		if (area_alias == MAP_FAILED)
 			err("mmap of hugetlb file alias failed");
 	}
 
 	if (*alloc_area == area_src) {
-		huge_fd_off0 = *alloc_area;
 		alloc_area_alias = &area_src_alias;
 	} else {
 		alloc_area_alias = &area_dst_alias;
@@ -270,12 +283,7 @@ static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset
 {
 	if (!map_shared)
 		return;
-	/*
-	 * We can't zap just the pagetable with hugetlbfs because
-	 * MADV_DONTEED won't work. So exercise -EEXIST on a alias
-	 * mapping where the pagetables are not established initially,
-	 * this way we'll exercise the -EEXEC at the fs level.
-	 */
+
 	*start = (unsigned long) area_dst_alias + offset;
 }
 
@@ -428,7 +436,6 @@ static void uffd_test_ctx_clear(void)
 		uffd = -1;
 	}
 
-	huge_fd_off0 = NULL;
 	munmap_area((void **)&area_src);
 	munmap_area((void **)&area_src_alias);
 	munmap_area((void **)&area_dst);
@@ -926,10 +933,7 @@ static int faulting_process(int signal_test)
 	struct sigaction act;
 	unsigned long signalled = 0;
 
-	if (test_type != TEST_HUGETLB)
-		split_nr_pages = (nr_pages + 1) / 2;
-	else
-		split_nr_pages = nr_pages;
+	split_nr_pages = (nr_pages + 1) / 2;
 
 	if (signal_test) {
 		sigbuf = &jbuf;
@@ -986,9 +990,6 @@ static int faulting_process(int signal_test)
 	if (signal_test)
 		return signalled != split_nr_pages;
 
-	if (test_type == TEST_HUGETLB)
-		return 0;
-
 	area_dst = mremap(area_dst, nr_pages * page_size,  nr_pages * page_size,
 			  MREMAP_MAYMOVE | MREMAP_FIXED, area_src);
 	if (area_dst == MAP_FAILED)
@@ -1676,7 +1677,7 @@ int main(int argc, char **argv)
 	}
 	nr_pages = nr_pages_per_cpu * nr_cpus;
 
-	if (test_type == TEST_HUGETLB) {
+	if (test_type == TEST_HUGETLB && map_shared) {
 		if (argc < 5)
 			usage();
 		huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755);
diff --git a/tools/testing/selftests/vm/util.h b/tools/testing/selftests/vm/util.h
new file mode 100644
index 000000000000..b27d26199334
--- /dev/null
+++ b/tools/testing/selftests/vm/util.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __KSELFTEST_VM_UTIL_H
+#define __KSELFTEST_VM_UTIL_H
+
+#include <stdint.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <string.h> /* ffsl() */
+#include <unistd.h> /* _SC_PAGESIZE */
+
+static unsigned int __page_size;
+static unsigned int __page_shift;
+
+static inline unsigned int page_size(void)
+{
+	if (!__page_size)
+		__page_size = sysconf(_SC_PAGESIZE);
+	return __page_size;
+}
+
+static inline unsigned int page_shift(void)
+{
+	if (!__page_shift)
+		__page_shift = (ffsl(page_size()) - 1);
+	return __page_shift;
+}
+
+#define PAGE_SHIFT	(page_shift())
+#define PAGE_SIZE	(page_size())
+/*
+ * On ppc64 this will only work with radix 2M hugepage size
+ */
+#define HPAGE_SHIFT 21
+#define HPAGE_SIZE (1 << HPAGE_SHIFT)
+
+#define PAGEMAP_PRESENT(ent)	(((ent) & (1ull << 63)) != 0)
+#define PAGEMAP_PFN(ent)	((ent) & ((1ull << 55) - 1))
+
+
+static inline int64_t allocate_transhuge(void *ptr, int pagemap_fd)
+{
+	uint64_t ent[2];
+
+	/* drop pmd */
+	if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
+		 MAP_FIXED | MAP_ANONYMOUS |
+		 MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+		errx(2, "mmap transhuge");
+
+	if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
+		err(2, "MADV_HUGEPAGE");
+
+	/* allocate transparent huge page */
+	*(volatile void **)ptr = ptr;
+
+	if (pread(pagemap_fd, ent, sizeof(ent),
+		  (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent))
+		err(2, "read pagemap");
+
+	if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) &&
+	    PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) &&
+	    !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1)))
+		return PAGEMAP_PFN(ent[0]);
+
+	return -1;
+}
+
+#endif
diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c
index 9ebb84a9c731..7679335fce5b 100644
--- a/tools/vm/page_owner_sort.c
+++ b/tools/vm/page_owner_sort.c
@@ -20,21 +20,56 @@
 #include <string.h>
 #include <regex.h>
 #include <errno.h>
+#include <linux/types.h>
+#include <getopt.h>
+
+#define bool int
+#define true 1
+#define false 0
+#define TASK_COMM_LEN 16
 
 struct block_list {
 	char *txt;
+	char *comm; // task command name
+	char *stacktrace;
+	__u64 ts_nsec;
+	__u64 free_ts_nsec;
 	int len;
 	int num;
 	int page_num;
+	pid_t pid;
+	pid_t tgid;
 };
-
-static int sort_by_memory;
+enum FILTER_BIT {
+	FILTER_UNRELEASE = 1<<1,
+	FILTER_PID = 1<<2,
+	FILTER_TGID = 1<<3,
+	FILTER_COMM = 1<<4
+};
+enum CULL_BIT {
+	CULL_UNRELEASE = 1<<1,
+	CULL_PID = 1<<2,
+	CULL_TGID = 1<<3,
+	CULL_COMM = 1<<4,
+	CULL_STACKTRACE = 1<<5
+};
+struct filter_condition {
+	pid_t tgid;
+	pid_t pid;
+	char comm[TASK_COMM_LEN];
+};
+static struct filter_condition fc;
 static regex_t order_pattern;
+static regex_t pid_pattern;
+static regex_t tgid_pattern;
+static regex_t comm_pattern;
+static regex_t ts_nsec_pattern;
+static regex_t free_ts_nsec_pattern;
 static struct block_list *list;
 static int list_size;
 static int max_size;
-
-struct block_list *block_head;
+static int cull;
+static int filter;
 
 int read_block(char *buf, int buf_size, FILE *fin)
 {
@@ -58,6 +93,13 @@ static int compare_txt(const void *p1, const void *p2)
 	return strcmp(l1->txt, l2->txt);
 }
 
+static int compare_stacktrace(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return strcmp(l1->stacktrace, l2->stacktrace);
+}
+
 static int compare_num(const void *p1, const void *p2)
 {
 	const struct block_list *l1 = p1, *l2 = p2;
@@ -72,41 +114,260 @@ static int compare_page_num(const void *p1, const void *p2)
 	return l2->page_num - l1->page_num;
 }
 
-static int get_page_num(char *buf)
+static int compare_pid(const void *p1, const void *p2)
 {
-	int err, val_len, order_val;
-	char order_str[4] = {0};
-	char *endptr;
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l1->pid - l2->pid;
+}
+
+static int compare_tgid(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l1->tgid - l2->tgid;
+}
+
+static int compare_comm(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return strcmp(l1->comm, l2->comm);
+}
+
+static int compare_ts(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l1->ts_nsec < l2->ts_nsec ? -1 : 1;
+}
+
+static int compare_free_ts(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	return l1->free_ts_nsec < l2->free_ts_nsec ? -1 : 1;
+}
+
+
+static int compare_release(const void *p1, const void *p2)
+{
+	const struct block_list *l1 = p1, *l2 = p2;
+
+	if (!l1->free_ts_nsec && !l2->free_ts_nsec)
+		return 0;
+	if (l1->free_ts_nsec && l2->free_ts_nsec)
+		return 0;
+	return l1->free_ts_nsec ? 1 : -1;
+}
+
+
+static int compare_cull_condition(const void *p1, const void *p2)
+{
+	if (cull == 0)
+		return compare_txt(p1, p2);
+	if ((cull & CULL_STACKTRACE) && compare_stacktrace(p1, p2))
+		return compare_stacktrace(p1, p2);
+	if ((cull & CULL_PID) && compare_pid(p1, p2))
+		return compare_pid(p1, p2);
+	if ((cull & CULL_TGID) && compare_tgid(p1, p2))
+		return compare_tgid(p1, p2);
+	if ((cull & CULL_COMM) && compare_comm(p1, p2))
+		return compare_comm(p1, p2);
+	if ((cull & CULL_UNRELEASE) && compare_release(p1, p2))
+		return compare_release(p1, p2);
+	return 0;
+}
+
+static int search_pattern(regex_t *pattern, char *pattern_str, char *buf)
+{
+	int err, val_len;
 	regmatch_t pmatch[2];
 
-	err = regexec(&order_pattern, buf, 2, pmatch, REG_NOTBOL);
+	err = regexec(pattern, buf, 2, pmatch, REG_NOTBOL);
 	if (err != 0 || pmatch[1].rm_so == -1) {
-		printf("no order pattern in %s\n", buf);
-		return 0;
+		printf("no matching pattern in %s\n", buf);
+		return -1;
 	}
 	val_len = pmatch[1].rm_eo - pmatch[1].rm_so;
-	if (val_len > 2) /* max_order should not exceed 2 digits */
-		goto wrong_order;
 
-	memcpy(order_str, buf + pmatch[1].rm_so, val_len);
+	memcpy(pattern_str, buf + pmatch[1].rm_so, val_len);
+
+	return 0;
+}
+
+static void check_regcomp(regex_t *pattern, const char *regex)
+{
+	int err;
+
+	err = regcomp(pattern, regex, REG_EXTENDED | REG_NEWLINE);
+	if (err != 0 || pattern->re_nsub != 1) {
+		printf("Invalid pattern %s code %d\n", regex, err);
+		exit(1);
+	}
+}
 
+static char **explode(char sep, const char *str, int *size)
+{
+	int count = 0, len = strlen(str);
+	int lastindex = -1, j = 0;
+
+	for (int i = 0; i < len; i++)
+		if (str[i] == sep)
+			count++;
+	char **ret = calloc(++count, sizeof(char *));
+
+	for (int i = 0; i < len; i++) {
+		if (str[i] == sep) {
+			ret[j] = calloc(i - lastindex, sizeof(char));
+			memcpy(ret[j++], str + lastindex + 1, i - lastindex - 1);
+			lastindex = i;
+		}
+	}
+	if (lastindex <= len - 1) {
+		ret[j] = calloc(len - lastindex, sizeof(char));
+		memcpy(ret[j++], str + lastindex + 1, strlen(str) - 1 - lastindex);
+	}
+	*size = j;
+	return ret;
+}
+
+static void free_explode(char **arr, int size)
+{
+	for (int i = 0; i < size; i++)
+		free(arr[i]);
+	free(arr);
+}
+
+# define FIELD_BUFF 25
+
+static int get_page_num(char *buf)
+{
+	int order_val;
+	char order_str[FIELD_BUFF] = {0};
+	char *endptr;
+
+	search_pattern(&order_pattern, order_str, buf);
 	errno = 0;
 	order_val = strtol(order_str, &endptr, 10);
-	if (errno != 0 || endptr == order_str || *endptr != '\0')
-		goto wrong_order;
+	if (order_val > 64 || errno != 0 || endptr == order_str || *endptr != '\0') {
+		printf("wrong order in follow buf:\n%s\n", buf);
+		return 0;
+	}
 
 	return 1 << order_val;
+}
+
+static pid_t get_pid(char *buf)
+{
+	pid_t pid;
+	char pid_str[FIELD_BUFF] = {0};
+	char *endptr;
+
+	search_pattern(&pid_pattern, pid_str, buf);
+	errno = 0;
+	pid = strtol(pid_str, &endptr, 10);
+	if (errno != 0 || endptr == pid_str || *endptr != '\0') {
+		printf("wrong/invalid pid in follow buf:\n%s\n", buf);
+		return -1;
+	}
+
+	return pid;
 
-wrong_order:
-	printf("wrong order in follow buf:\n%s\n", buf);
-	return 0;
+}
+
+static pid_t get_tgid(char *buf)
+{
+	pid_t tgid;
+	char tgid_str[FIELD_BUFF] = {0};
+	char *endptr;
+
+	search_pattern(&tgid_pattern, tgid_str, buf);
+	errno = 0;
+	tgid = strtol(tgid_str, &endptr, 10);
+	if (errno != 0 || endptr == tgid_str || *endptr != '\0') {
+		printf("wrong/invalid tgid in follow buf:\n%s\n", buf);
+		return -1;
+	}
+
+	return tgid;
+
+}
+
+static __u64 get_ts_nsec(char *buf)
+{
+	__u64 ts_nsec;
+	char ts_nsec_str[FIELD_BUFF] = {0};
+	char *endptr;
+
+	search_pattern(&ts_nsec_pattern, ts_nsec_str, buf);
+	errno = 0;
+	ts_nsec = strtoull(ts_nsec_str, &endptr, 10);
+	if (errno != 0 || endptr == ts_nsec_str || *endptr != '\0') {
+		printf("wrong ts_nsec in follow buf:\n%s\n", buf);
+		return -1;
+	}
+
+	return ts_nsec;
+}
+
+static __u64 get_free_ts_nsec(char *buf)
+{
+	__u64 free_ts_nsec;
+	char free_ts_nsec_str[FIELD_BUFF] = {0};
+	char *endptr;
+
+	search_pattern(&free_ts_nsec_pattern, free_ts_nsec_str, buf);
+	errno = 0;
+	free_ts_nsec = strtoull(free_ts_nsec_str, &endptr, 10);
+	if (errno != 0 || endptr == free_ts_nsec_str || *endptr != '\0') {
+		printf("wrong free_ts_nsec in follow buf:\n%s\n", buf);
+		return -1;
+	}
+
+	return free_ts_nsec;
+}
+
+static char *get_comm(char *buf)
+{
+	char *comm_str = malloc(TASK_COMM_LEN);
+
+	memset(comm_str, 0, TASK_COMM_LEN);
+
+	search_pattern(&comm_pattern, comm_str, buf);
+	errno = 0;
+	if (errno != 0) {
+		printf("wrong comm in follow buf:\n%s\n", buf);
+		return NULL;
+	}
+
+	return comm_str;
+}
+
+static bool is_need(char *buf)
+{
+		if ((filter & FILTER_UNRELEASE) && get_free_ts_nsec(buf) != 0)
+			return false;
+		if ((filter & FILTER_PID) && get_pid(buf) != fc.pid)
+			return false;
+		if ((filter & FILTER_TGID) && get_tgid(buf) != fc.tgid)
+			return false;
+
+		char *comm = get_comm(buf);
+
+		if ((filter & FILTER_COMM) &&
+		strncmp(comm, fc.comm, TASK_COMM_LEN) != 0) {
+			free(comm);
+			return false;
+		}
+		return true;
 }
 
 static void add_list(char *buf, int len)
 {
 	if (list_size != 0 &&
-	    len == list[list_size-1].len &&
-	    memcmp(buf, list[list_size-1].txt, len) == 0) {
+		len == list[list_size-1].len &&
+		memcmp(buf, list[list_size-1].txt, len) == 0) {
 		list[list_size-1].num++;
 		list[list_size-1].page_num += get_page_num(buf);
 		return;
@@ -115,12 +376,27 @@ static void add_list(char *buf, int len)
 		printf("max_size too small??\n");
 		exit(1);
 	}
+	if (!is_need(buf))
+		return;
+	list[list_size].pid = get_pid(buf);
+	list[list_size].tgid = get_tgid(buf);
+	list[list_size].comm = get_comm(buf);
 	list[list_size].txt = malloc(len+1);
+	if (!list[list_size].txt) {
+		printf("Out of memory\n");
+		exit(1);
+	}
+	memcpy(list[list_size].txt, buf, len);
+	list[list_size].txt[len] = 0;
 	list[list_size].len = len;
 	list[list_size].num = 1;
 	list[list_size].page_num = get_page_num(buf);
-	memcpy(list[list_size].txt, buf, len);
-	list[list_size].txt[len] = 0;
+
+	list[list_size].stacktrace = strchr(list[list_size].txt, '\n') ?: "";
+	if (*list[list_size].stacktrace == '\n')
+		list[list_size].stacktrace++;
+	list[list_size].ts_nsec = get_ts_nsec(buf);
+	list[list_size].free_ts_nsec = get_free_ts_nsec(buf);
 	list_size++;
 	if (list_size % 1000 == 0) {
 		printf("loaded %d\r", list_size);
@@ -128,29 +404,129 @@ static void add_list(char *buf, int len)
 	}
 }
 
+static bool parse_cull_args(const char *arg_str)
+{
+	int size = 0;
+	char **args = explode(',', arg_str, &size);
+
+	for (int i = 0; i < size; ++i)
+		if (!strcmp(args[i], "pid") || !strcmp(args[i], "p"))
+			cull |= CULL_PID;
+		else if (!strcmp(args[i], "tgid") || !strcmp(args[i], "tg"))
+			cull |= CULL_TGID;
+		else if (!strcmp(args[i], "name") || !strcmp(args[i], "n"))
+			cull |= CULL_COMM;
+		else if (!strcmp(args[i], "stacktrace") || !strcmp(args[i], "st"))
+			cull |= CULL_STACKTRACE;
+		else if (!strcmp(args[i], "free") || !strcmp(args[i], "f"))
+			cull |= CULL_UNRELEASE;
+		else {
+			free_explode(args, size);
+			return false;
+		}
+	free_explode(args, size);
+	return true;
+}
+
 #define BUF_SIZE	(128 * 1024)
 
 static void usage(void)
 {
-	printf("Usage: ./page_owner_sort [-m] <input> <output>\n"
-		"-m	Sort by total memory. If this option is unset, sort by times\n"
+	printf("Usage: ./page_owner_sort [OPTIONS] <input> <output>\n"
+		"-m\t\tSort by total memory.\n"
+		"-s\t\tSort by the stack trace.\n"
+		"-t\t\tSort by times (default).\n"
+		"-p\t\tSort by pid.\n"
+		"-P\t\tSort by tgid.\n"
+		"-n\t\tSort by task command name.\n"
+		"-a\t\tSort by memory allocate time.\n"
+		"-r\t\tSort by memory release time.\n"
+		"-c\t\tCull by comparing stacktrace instead of total block.\n"
+		"-f\t\tFilter out the information of blocks whose memory has been released.\n"
+		"--pid <PID>\tSelect by pid. This selects the information of blocks whose process ID number equals to <PID>.\n"
+		"--tgid <TGID>\tSelect by tgid. This selects the information of blocks whose Thread Group ID number equals to <TGID>.\n"
+		"--name <command>\n\t\tSelect by command name. This selects the information of blocks whose command name identical to <command>.\n"
+		"--cull <rules>\tCull by user-defined rules. <rules> is a single argument in the form of a comma-separated list with some common fields predefined\n"
 	);
 }
 
 int main(int argc, char **argv)
 {
+	int (*cmp)(const void *, const void *) = compare_num;
 	FILE *fin, *fout;
-	char *buf;
+	char *buf, *endptr;
 	int ret, i, count;
-	struct block_list *list2;
 	struct stat st;
-	int err;
 	int opt;
-
-	while ((opt = getopt(argc, argv, "m")) != -1)
+	struct option longopts[] = {
+		{ "pid", required_argument, NULL, 1 },
+		{ "tgid", required_argument, NULL, 2 },
+		{ "name", required_argument, NULL, 3 },
+		{ "cull",  required_argument, NULL, 4 },
+		{ 0, 0, 0, 0},
+	};
+
+	while ((opt = getopt_long(argc, argv, "acfmnprstP", longopts, NULL)) != -1)
 		switch (opt) {
+		case 'a':
+			cmp = compare_ts;
+			break;
+		case 'c':
+			cull = cull | CULL_STACKTRACE;
+			break;
+		case 'f':
+			filter = filter | FILTER_UNRELEASE;
+			break;
 		case 'm':
-			sort_by_memory = 1;
+			cmp = compare_page_num;
+			break;
+		case 'p':
+			cmp = compare_pid;
+			break;
+		case 'r':
+			cmp = compare_free_ts;
+			break;
+		case 's':
+			cmp = compare_stacktrace;
+			break;
+		case 't':
+			cmp = compare_num;
+			break;
+		case 'P':
+			cmp = compare_tgid;
+			break;
+		case 'n':
+			cmp = compare_comm;
+			break;
+		case 1:
+			filter = filter | FILTER_PID;
+			errno = 0;
+			fc.pid = strtol(optarg, &endptr, 10);
+			if (errno != 0 || endptr == optarg || *endptr != '\0') {
+				printf("wrong/invalid pid in from the command line:%s\n", optarg);
+				exit(1);
+			}
+			break;
+		case 2:
+			filter = filter | FILTER_TGID;
+			errno = 0;
+			fc.tgid = strtol(optarg, &endptr, 10);
+			if (errno != 0 || endptr == optarg || *endptr != '\0') {
+				printf("wrong/invalid tgid in from the command line:%s\n", optarg);
+				exit(1);
+			}
+			break;
+		case 3:
+			filter = filter | FILTER_COMM;
+			strncpy(fc.comm, optarg, TASK_COMM_LEN);
+			fc.comm[TASK_COMM_LEN-1] = '\0';
+			break;
+		case 4:
+			if (!parse_cull_args(optarg)) {
+				printf("wrong argument after --cull in from the command line:%s\n",
+						optarg);
+				exit(1);
+			}
 			break;
 		default:
 			usage();
@@ -170,13 +546,12 @@ int main(int argc, char **argv)
 		exit(1);
 	}
 
-	err = regcomp(&order_pattern, "order\\s*([0-9]*),", REG_EXTENDED|REG_NEWLINE);
-	if (err != 0 || order_pattern.re_nsub != 1) {
-		printf("%s: Invalid pattern 'order\\s*([0-9]*),' code %d\n",
-			argv[0], err);
-		exit(1);
-	}
-
+	check_regcomp(&order_pattern, "order\\s*([0-9]*),");
+	check_regcomp(&pid_pattern, "pid\\s*([0-9]*),");
+	check_regcomp(&tgid_pattern, "tgid\\s*([0-9]*) ");
+	check_regcomp(&comm_pattern, "tgid\\s*[0-9]*\\s*\\((.*)\\),\\s*ts");
+	check_regcomp(&ts_nsec_pattern, "ts\\s*([0-9]*)\\s*ns,");
+	check_regcomp(&free_ts_nsec_pattern, "free_ts\\s*([0-9]*)\\s*ns");
 	fstat(fileno(fin), &st);
 	max_size = st.st_size / 100; /* hack ... */
 
@@ -199,35 +574,48 @@ int main(int argc, char **argv)
 
 	printf("sorting ....\n");
 
-	qsort(list, list_size, sizeof(list[0]), compare_txt);
-
-	list2 = malloc(sizeof(*list) * list_size);
-	if (!list2) {
-		printf("Out of memory\n");
-		exit(1);
-	}
+	qsort(list, list_size, sizeof(list[0]), compare_cull_condition);
 
 	printf("culling\n");
 
 	for (i = count = 0; i < list_size; i++) {
 		if (count == 0 ||
-		    strcmp(list2[count-1].txt, list[i].txt) != 0) {
-			list2[count++] = list[i];
+		    compare_cull_condition((void *)(&list[count-1]), (void *)(&list[i])) != 0) {
+			list[count++] = list[i];
 		} else {
-			list2[count-1].num += list[i].num;
-			list2[count-1].page_num += list[i].page_num;
+			list[count-1].num += list[i].num;
+			list[count-1].page_num += list[i].page_num;
 		}
 	}
 
-	if (sort_by_memory)
-		qsort(list2, count, sizeof(list[0]), compare_page_num);
-	else
-		qsort(list2, count, sizeof(list[0]), compare_num);
-
-	for (i = 0; i < count; i++)
-		fprintf(fout, "%d times, %d pages:\n%s\n",
-				list2[i].num, list2[i].page_num, list2[i].txt);
-
+	qsort(list, count, sizeof(list[0]), cmp);
+
+	for (i = 0; i < count; i++) {
+		if (cull == 0)
+			fprintf(fout, "%d times, %d pages:\n%s\n",
+					list[i].num, list[i].page_num, list[i].txt);
+		else {
+			fprintf(fout, "%d times, %d pages",
+					list[i].num, list[i].page_num);
+			if (cull & CULL_PID || filter & FILTER_PID)
+				fprintf(fout, ", PID %d", list[i].pid);
+			if (cull & CULL_TGID || filter & FILTER_TGID)
+				fprintf(fout, ", TGID %d", list[i].pid);
+			if (cull & CULL_COMM || filter & FILTER_COMM)
+				fprintf(fout, ", task_comm_name: %s", list[i].comm);
+			if (cull & CULL_UNRELEASE)
+				fprintf(fout, " (%s)",
+						list[i].free_ts_nsec ? "UNRELEASED" : "RELEASED");
+			if (cull & CULL_STACKTRACE)
+				fprintf(fout, ":\n%s", list[i].stacktrace);
+			fprintf(fout, "\n");
+		}
+	}
 	regfree(&order_pattern);
+	regfree(&pid_pattern);
+	regfree(&tgid_pattern);
+	regfree(&comm_pattern);
+	regfree(&ts_nsec_pattern);
+	regfree(&free_ts_nsec_pattern);
 	return 0;
 }